© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6808
    Prev
    Next
    INDEX
    Explanations

    tokens representing diverse languages and their unique characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.11
    0.5%
    595
    +0.10
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.14
    317
    +0.10
    0.13
    621
    +0.09
    0.12
    Negative Logits
     Quadro
    -0.76
     Sands
    -0.76
     Dill
    -0.74
    espie
    -0.71
     Schn
    -0.69
     skelet
    -0.69
     Nielsen
    -0.68
    boro
    -0.65
     Ferr
    -0.65
     Sinclair
    -0.65
    POSITIVE LOGITS
    Ľ
    1.51
    Ģ
    1.31
    ŃĶ
    1.31
    Ķ
    1.30
    ı
    1.29
    Ī
    1.28
    ķ
    1.28
    Ĵ
    1.27
    ĥ
    1.26
    ¦
    1.26
    Activations Density 0.961%

    No Known Activations